ExtractorError,
UnsupportedError,
determine_ext,
+ determine_protocol,
dict_get,
extract_basic_auth,
format_field,
},
},
{
- # Video.js embed, multiple formats
+ # Youtube embed, formerly: Video.js embed, multiple formats
'url': 'http://ortcam.com/solidworks-урок-6-настройка-чертежа_33f9b7351.html',
'info_dict': {
'id': 'yygqldloqIk',
'params': {
'skip_download': True,
},
+ 'skip': '404 Not Found',
},
# rtl.nl embed
{
'age_limit': 18,
},
},
+ {
+ 'note': 'Live HLS direct link',
+ 'url': 'https://d18j67ugtrocuq.cloudfront.net/out/v1/2767aec339144787926bd0322f72c6e9/index.m3u8',
+ 'info_dict': {
+ 'id': 'index',
+ 'title': r're:index',
+ 'ext': 'mp4',
+ 'live_status': 'is_live',
+ },
+ 'params': {
+ 'skip_download': 'm3u8',
+ },
+ },
+ {
+ 'note': 'Video.js VOD HLS',
+ 'url': 'https://gist.githubusercontent.com/bashonly/2aae0862c50f4a4b84f220c315767208/raw/e3380d413749dabbe804c9c2d8fd9a45142475c7/videojs_hls_test.html',
+ 'info_dict': {
+ 'id': 'videojs_hls_test',
+ 'title': 'video',
+ 'ext': 'mp4',
+ 'age_limit': 0,
+ 'duration': 1800,
+ },
+ 'params': {
+ 'skip_download': 'm3u8',
+ },
+ },
]
def report_following_redirect(self, new_url):
for fmt in self._downloader._get_formats(info):
fmt['url'] = update_url_query(fmt['url'], query)
+ # Attempt to detect live HLS or set VOD duration
+ m3u8_format = next((f for f in self._downloader._get_formats(info)
+ if determine_protocol(f) == 'm3u8_native'), None)
+ if m3u8_format:
+ is_live = self._configuration_arg('is_live', [None])[0]
+ if is_live is not None:
+ info['live_status'] = 'not_live' if is_live == 'false' else 'is_live'
+ return
+ headers = m3u8_format.get('http_headers') or info.get('http_headers')
+ duration = self._extract_m3u8_vod_duration(
+ m3u8_format['url'], info.get('id'), note='Checking m3u8 live status',
+ errnote='Failed to download m3u8 media playlist', headers=headers)
+ if not duration:
+ info['live_status'] = 'is_live'
+ info['duration'] = info.get('duration') or duration
+
def _extract_rss(self, url, video_id, doc):
NS_MAP = {
'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
varname = mobj.group(1)
sources = variadic(self._parse_json(
mobj.group(2), video_id, transform_source=js_to_json, fatal=False) or [])
- formats = []
- subtitles = {}
+ formats, subtitles, src = [], {}, None
for source in sources:
src = source.get('src')
if not src or not isinstance(src, str):
m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
- for fmt in formats:
- self._extra_manifest_info(fmt, src)
if not formats:
formats.append({
for sub_match in re.finditer(rf'(?s){re.escape(varname)}' r'\.addRemoteTextTrack\(({.+?})\s*,\s*(?:true|false)\)', webpage):
sub = self._parse_json(
sub_match.group(1), video_id, transform_source=js_to_json, fatal=False) or {}
- src = str_or_none(sub.get('src'))
- if not src:
+ sub_src = str_or_none(sub.get('src'))
+ if not sub_src:
continue
subtitles.setdefault(dict_get(sub, ('language', 'srclang')) or 'und', []).append({
- 'url': urllib.parse.urljoin(url, src),
+ 'url': urllib.parse.urljoin(url, sub_src),
'name': sub.get('label'),
'http_headers': {
'Referer': actual_url,
})
if formats or subtitles:
self.report_detected('video.js embed')
- return [{'formats': formats, 'subtitles': subtitles}]
+ info_dict = {'formats': formats, 'subtitles': subtitles}
+ if formats:
+ self._extra_manifest_info(info_dict, src)
+ return [info_dict]
# Look for generic KVS player (before json-ld bc of some urls that break otherwise)
found = self._search_regex((